Revision as of 01:57, 23 November 2007 edit 68.40.60.9 (talk) No edit summary ← Previous edit		Revision as of 01:58, 23 November 2007 edit undo 68.40.60.9 (talk) No edit summary Next edit →
Line 1: == Introduction == Line 18 ⟶ 17: An auto-encoder is often trained using one of the many backpropagation variants (Conjugate Gradient Method, Steepest Descen, etc.) A technique developed Geoffrey Hinton for training many-layered "deep" auto-encoders involves treating each set of two layers like a [[~~Restricted Boltzmann Machine~~Boltzmann_machine#Restricted_Boltzmann_Machine]] for pre-training to approximate a good solution and then using a backpropagation technique to fine-tune.

Autoencoder: Difference between revisions